ESM 244 Lab 1 Satie

Read in SF trees data

sf_trees <- read_csv(here("data", "sf_trees", "sf_trees.csv"))

## Parsed with column specification:
## cols(
##   tree_id = col_double(),
##   legal_status = col_character(),
##   species = col_character(),
##   address = col_character(),
##   site_order = col_double(),
##   site_info = col_character(),
##   caretaker = col_character(),
##   date = col_date(format = ""),
##   dbh = col_double(),
##   plot_size = col_character(),
##   latitude = col_double(),
##   longitude = col_double()
## )

Basic wrangling reminders

Refresh some skills for data wrangling and summary statistics using functions in the ‘dplyr’ package. Find the top five highest observations of trees by legal_status, do some wrangling, make a graph.

top_5_status <- sf_trees %>% 
  count(legal_status) %>%  # recognize groups, finding counts, in a table
  drop_na(legal_status) %>%  # to remove missing values labeled NA
  rename(tree_count = n) %>% # new name goes on the left, old name on the right
  relocate(tree_count) %>%  # moves tree_count to first column position
  slice_max(tree_count, n = 5) # indicate in which colunn to look and the number you want to present, there is also slice_min available

Make a graph of top five observations by legal status

ggplot(data = top_5_status, aes(x = fct_reorder(legal_status, tree_count), y = tree_count)) + # uce fct_reorder to reorganize data in order of tree_count, alternative to use convert to factor and use fct_reorder
  geom_col() +
  labs(x = "Legal Status", y = "Tree Count") +
  coord_flip() + # flip the axes in case the names are too long on x axis
  theme_minimal()

A few more data wrangling refresher examples

Only keep observations (rows) for Blackwood Acacia Trees

blackwood_acacia <- sf_trees %>% 
  filter(str_detect(species, "Blackwood Acacia")) %>% # looks within a variable (sf_trees data) that we specify to identify if there are any strings there, does not need to be a complete match, just part of the string
  select(legal_status, date, latitude, longitude) # pick columns that you want to pick or exclude

ggplot(data = blackwood_acacia, aes(x = longitude, y = latitude)) +
  geom_point()

## Warning: Removed 27 rows containing missing values (geom_point).

tidyr::separate() and unite() functions

Useful for combining and separating columns

sf_trees_sep <- sf_trees %>% 
  separate(species, into =
c("spp_scientific", "spp_common"), sep = "::") # separate one column into two columns using data within that column, create a vector c with two new columns, then name the separator (::)

Exampe: tidyr::unite()

sf_trees_unite <- sf_trees %>% 
  unite("id_status", tree_id:legal_status, sep = "_cool!_") # combine two columns into one and add a separator ("_cool!_"), could use a vector or use a colon, which indicates "from this column to that column"

Make some actual maps of blackwood acacia trees in SF

‘st_as_sf()’ to convert latitude and longitude to spatial coordinates

blackwood_acacia_spatial <- blackwood_acacia %>% 
  drop_na(longitude, latitude) %>% 
  st_as_sf(coords = c("longitude", "latitude")) # converts longitude and latitude to spatial data, use longitude first, then latitude second

st_crs(blackwood_acacia_spatial) = 4326 # 4-digit code from European Petroleum Survey Group for what the coordinate reference system is.

ggplot(data = blackwood_acacia_spatial) +
  geom_sf(color = "darkgreen") + 
  labs(x = "Latitude",
       y = "Longitude")

Read in SF roads shapefile

sf_map <- read_sf(here("data", "sf_map", "tl_2017_06075_roads.shp"))

Run in Console: # “st_transform(sf_map)” to look for existing projection information There is an existing CSR for the roads shapefile so we need to use st_transform.

st_transform(sf_map, 4326)

## Simple feature collection with 4087 features and 4 fields
## geometry type:  LINESTRING
## dimension:      XY
## bbox:           xmin: -122.5136 ymin: 37.70813 xmax: -122.3496 ymax: 37.83213
## geographic CRS: WGS 84
## # A tibble: 4,087 x 5
##    LINEARID   FULLNAME     RTTYP MTFCC                                  geometry
##  * <chr>      <chr>        <chr> <chr>                          <LINESTRING [°]>
##  1 110498938… Hwy 101 S O… M     S1400 (-122.4041 37.74842, -122.404 37.7483, -…
##  2 110498937… Hwy 101 N o… M     S1400 (-122.4744 37.80691, -122.4746 37.80684,…
##  3 110366022… Ludlow Aly … M     S1780 (-122.4596 37.73853, -122.4596 37.73845,…
##  4 110608181… Mission Bay… M     S1400 (-122.3946 37.77082, -122.3929 37.77092,…
##  5 110366689… 25th Ave N   M     S1400 (-122.4858 37.78953, -122.4855 37.78935,…
##  6 110368970… Willard N    M     S1400 (-122.457 37.77817, -122.457 37.77812, -…
##  7 110368970… 25th Ave N   M     S1400 (-122.4858 37.78953, -122.4858 37.78952,…
##  8 110498933… Avenue N     M     S1400 (-122.3643 37.81947, -122.3638 37.82064,…
##  9 110368970… 25th Ave N   M     S1400  (-122.4854 37.78983, -122.4858 37.78953)
## 10 110367749… Mission Bay… M     S1400 (-122.3865 37.77086, -122.3878 37.77076,…
## # … with 4,077 more rows

ggplot(data = sf_map) +
  geom_sf()

Combine blackwood acacia tree observations and SF roads map

ggplot() +
  geom_sf(data = sf_map, size = 0.1, color = "darkgray") +
  geom_sf(data = blackwood_acacia_spatial, color = "red", size = 0.5) +
  theme_void()

maybe install leaflet

Now an interactive map:

tmap_mode("view") # default is "plot" which is static, "view" is interactive

## tmap mode set to interactive viewing

tm_shape(blackwood_acacia_spatial) +
  tm_dots()